{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9988221436984688,
  "eval_steps": 80,
  "global_step": 318,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0031409501374165686,
      "grad_norm": 5.125,
      "learning_rate": 2e-05,
      "loss": 10.7953,
      "step": 1
    },
    {
      "epoch": 0.0031409501374165686,
      "eval_loss": 10.810359001159668,
      "eval_runtime": 65.1601,
      "eval_samples_per_second": 39.917,
      "eval_steps_per_second": 39.917,
      "step": 1
    },
    {
      "epoch": 0.006281900274833137,
      "grad_norm": 4.59375,
      "learning_rate": 4e-05,
      "loss": 10.599,
      "step": 2
    },
    {
      "epoch": 0.009422850412249705,
      "grad_norm": 5.65625,
      "learning_rate": 6e-05,
      "loss": 10.8341,
      "step": 3
    },
    {
      "epoch": 0.012563800549666274,
      "grad_norm": 4.59375,
      "learning_rate": 8e-05,
      "loss": 10.2321,
      "step": 4
    },
    {
      "epoch": 0.015704750687082842,
      "grad_norm": 5.09375,
      "learning_rate": 0.0001,
      "loss": 9.926,
      "step": 5
    },
    {
      "epoch": 0.01884570082449941,
      "grad_norm": 5.09375,
      "learning_rate": 0.00012,
      "loss": 9.2807,
      "step": 6
    },
    {
      "epoch": 0.02198665096191598,
      "grad_norm": 5.21875,
      "learning_rate": 0.00014,
      "loss": 8.7401,
      "step": 7
    },
    {
      "epoch": 0.02512760109933255,
      "grad_norm": 5.3125,
      "learning_rate": 0.00016,
      "loss": 7.7479,
      "step": 8
    },
    {
      "epoch": 0.028268551236749116,
      "grad_norm": 3.78125,
      "learning_rate": 0.00018,
      "loss": 7.3356,
      "step": 9
    },
    {
      "epoch": 0.031409501374165684,
      "grad_norm": 4.15625,
      "learning_rate": 0.0002,
      "loss": 6.8649,
      "step": 10
    },
    {
      "epoch": 0.03455045151158225,
      "grad_norm": 1.9296875,
      "learning_rate": 0.00019999969015048862,
      "loss": 6.7994,
      "step": 11
    },
    {
      "epoch": 0.03769140164899882,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0001999987606038746,
      "loss": 6.2436,
      "step": 12
    },
    {
      "epoch": 0.040832351786415394,
      "grad_norm": 2.125,
      "learning_rate": 0.0001999972113659183,
      "loss": 6.6684,
      "step": 13
    },
    {
      "epoch": 0.04397330192383196,
      "grad_norm": 0.9921875,
      "learning_rate": 0.00019999504244622043,
      "loss": 6.4968,
      "step": 14
    },
    {
      "epoch": 0.04711425206124853,
      "grad_norm": 1.0625,
      "learning_rate": 0.00019999225385822165,
      "loss": 6.3331,
      "step": 15
    },
    {
      "epoch": 0.0502552021986651,
      "grad_norm": 0.88671875,
      "learning_rate": 0.00019998884561920284,
      "loss": 6.3441,
      "step": 16
    },
    {
      "epoch": 0.053396152336081665,
      "grad_norm": 1.171875,
      "learning_rate": 0.00019998481775028491,
      "loss": 5.8419,
      "step": 17
    },
    {
      "epoch": 0.05653710247349823,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0001999801702764284,
      "loss": 6.1942,
      "step": 18
    },
    {
      "epoch": 0.0596780526109148,
      "grad_norm": 1.75,
      "learning_rate": 0.00019997490322643376,
      "loss": 6.017,
      "step": 19
    },
    {
      "epoch": 0.06281900274833137,
      "grad_norm": 1.1875,
      "learning_rate": 0.00019996901663294078,
      "loss": 6.2501,
      "step": 20
    },
    {
      "epoch": 0.06595995288574794,
      "grad_norm": 0.9296875,
      "learning_rate": 0.00019996251053242865,
      "loss": 5.9597,
      "step": 21
    },
    {
      "epoch": 0.0691009030231645,
      "grad_norm": 1.8984375,
      "learning_rate": 0.0001999553849652156,
      "loss": 6.0591,
      "step": 22
    },
    {
      "epoch": 0.07224185316058107,
      "grad_norm": 1.265625,
      "learning_rate": 0.00019994763997545874,
      "loss": 6.2802,
      "step": 23
    },
    {
      "epoch": 0.07538280329799764,
      "grad_norm": 1.7265625,
      "learning_rate": 0.00019993927561115366,
      "loss": 6.082,
      "step": 24
    },
    {
      "epoch": 0.0785237534354142,
      "grad_norm": 1.0,
      "learning_rate": 0.00019993029192413424,
      "loss": 6.1596,
      "step": 25
    },
    {
      "epoch": 0.08166470357283079,
      "grad_norm": 1.609375,
      "learning_rate": 0.00019992068897007232,
      "loss": 5.9254,
      "step": 26
    },
    {
      "epoch": 0.08480565371024736,
      "grad_norm": 1.5234375,
      "learning_rate": 0.0001999104668084773,
      "loss": 5.893,
      "step": 27
    },
    {
      "epoch": 0.08794660384766392,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00019989962550269583,
      "loss": 6.1184,
      "step": 28
    },
    {
      "epoch": 0.09108755398508049,
      "grad_norm": 0.88671875,
      "learning_rate": 0.00019988816511991135,
      "loss": 5.9582,
      "step": 29
    },
    {
      "epoch": 0.09422850412249706,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00019987608573114376,
      "loss": 5.8845,
      "step": 30
    },
    {
      "epoch": 0.09736945425991363,
      "grad_norm": 1.3046875,
      "learning_rate": 0.0001998633874112489,
      "loss": 6.1202,
      "step": 31
    },
    {
      "epoch": 0.1005104043973302,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00019985007023891815,
      "loss": 5.7627,
      "step": 32
    },
    {
      "epoch": 0.10365135453474676,
      "grad_norm": 0.8828125,
      "learning_rate": 0.00019983613429667792,
      "loss": 6.0619,
      "step": 33
    },
    {
      "epoch": 0.10679230467216333,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00019982157967088904,
      "loss": 5.683,
      "step": 34
    },
    {
      "epoch": 0.1099332548095799,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0001998064064517464,
      "loss": 5.8008,
      "step": 35
    },
    {
      "epoch": 0.11307420494699646,
      "grad_norm": 1.375,
      "learning_rate": 0.00019979061473327837,
      "loss": 5.8867,
      "step": 36
    },
    {
      "epoch": 0.11621515508441303,
      "grad_norm": 1.671875,
      "learning_rate": 0.000199774204613346,
      "loss": 5.9331,
      "step": 37
    },
    {
      "epoch": 0.1193561052218296,
      "grad_norm": 1.4375,
      "learning_rate": 0.00019975717619364263,
      "loss": 5.4695,
      "step": 38
    },
    {
      "epoch": 0.12249705535924617,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0001997395295796933,
      "loss": 5.9711,
      "step": 39
    },
    {
      "epoch": 0.12563800549666274,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00019972126488085378,
      "loss": 5.7401,
      "step": 40
    },
    {
      "epoch": 0.12877895563407932,
      "grad_norm": 1.390625,
      "learning_rate": 0.00019970238221031034,
      "loss": 5.7064,
      "step": 41
    },
    {
      "epoch": 0.13191990577149587,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00019968288168507864,
      "loss": 5.6272,
      "step": 42
    },
    {
      "epoch": 0.13506085590891245,
      "grad_norm": 1.8359375,
      "learning_rate": 0.00019966276342600327,
      "loss": 5.4439,
      "step": 43
    },
    {
      "epoch": 0.138201806046329,
      "grad_norm": 1.265625,
      "learning_rate": 0.0001996420275577569,
      "loss": 5.9631,
      "step": 44
    },
    {
      "epoch": 0.1413427561837456,
      "grad_norm": 1.6796875,
      "learning_rate": 0.00019962067420883944,
      "loss": 5.8393,
      "step": 45
    },
    {
      "epoch": 0.14448370632116214,
      "grad_norm": 1.53125,
      "learning_rate": 0.00019959870351157747,
      "loss": 5.7997,
      "step": 46
    },
    {
      "epoch": 0.14762465645857872,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0001995761156021231,
      "loss": 5.656,
      "step": 47
    },
    {
      "epoch": 0.15076560659599528,
      "grad_norm": 1.4921875,
      "learning_rate": 0.00019955291062045345,
      "loss": 5.7152,
      "step": 48
    },
    {
      "epoch": 0.15390655673341186,
      "grad_norm": 1.828125,
      "learning_rate": 0.00019952908871036956,
      "loss": 5.7215,
      "step": 49
    },
    {
      "epoch": 0.1570475068708284,
      "grad_norm": 1.0,
      "learning_rate": 0.0001995046500194955,
      "loss": 5.6857,
      "step": 50
    },
    {
      "epoch": 0.160188457008245,
      "grad_norm": 1.3984375,
      "learning_rate": 0.00019947959469927772,
      "loss": 5.6698,
      "step": 51
    },
    {
      "epoch": 0.16332940714566158,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0001994539229049837,
      "loss": 5.2906,
      "step": 52
    },
    {
      "epoch": 0.16647035728307813,
      "grad_norm": 1.25,
      "learning_rate": 0.00019942763479570132,
      "loss": 5.4673,
      "step": 53
    },
    {
      "epoch": 0.1696113074204947,
      "grad_norm": 0.890625,
      "learning_rate": 0.00019940073053433777,
      "loss": 5.5959,
      "step": 54
    },
    {
      "epoch": 0.17275225755791127,
      "grad_norm": 1.59375,
      "learning_rate": 0.00019937321028761846,
      "loss": 5.9431,
      "step": 55
    },
    {
      "epoch": 0.17589320769532785,
      "grad_norm": 1.59375,
      "learning_rate": 0.00019934507422608608,
      "loss": 5.754,
      "step": 56
    },
    {
      "epoch": 0.1790341578327444,
      "grad_norm": 0.984375,
      "learning_rate": 0.00019931632252409955,
      "loss": 5.405,
      "step": 57
    },
    {
      "epoch": 0.18217510797016098,
      "grad_norm": 1.03125,
      "learning_rate": 0.00019928695535983287,
      "loss": 5.5907,
      "step": 58
    },
    {
      "epoch": 0.18531605810757754,
      "grad_norm": 1.2265625,
      "learning_rate": 0.00019925697291527415,
      "loss": 5.7941,
      "step": 59
    },
    {
      "epoch": 0.18845700824499412,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00019922637537622418,
      "loss": 5.6169,
      "step": 60
    },
    {
      "epoch": 0.19159795838241067,
      "grad_norm": 1.5,
      "learning_rate": 0.00019919516293229569,
      "loss": 5.5379,
      "step": 61
    },
    {
      "epoch": 0.19473890851982725,
      "grad_norm": 0.8203125,
      "learning_rate": 0.00019916333577691184,
      "loss": 5.6157,
      "step": 62
    },
    {
      "epoch": 0.1978798586572438,
      "grad_norm": 1.484375,
      "learning_rate": 0.00019913089410730526,
      "loss": 5.5043,
      "step": 63
    },
    {
      "epoch": 0.2010208087946604,
      "grad_norm": 0.98046875,
      "learning_rate": 0.00019909783812451664,
      "loss": 5.7083,
      "step": 64
    },
    {
      "epoch": 0.20416175893207694,
      "grad_norm": 1.125,
      "learning_rate": 0.00019906416803339353,
      "loss": 5.5739,
      "step": 65
    },
    {
      "epoch": 0.20730270906949352,
      "grad_norm": 1.375,
      "learning_rate": 0.00019902988404258922,
      "loss": 5.5447,
      "step": 66
    },
    {
      "epoch": 0.21044365920691008,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00019899498636456126,
      "loss": 5.3392,
      "step": 67
    },
    {
      "epoch": 0.21358460934432666,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0001989594752155702,
      "loss": 5.3176,
      "step": 68
    },
    {
      "epoch": 0.21672555948174324,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00019892335081567826,
      "loss": 5.1688,
      "step": 69
    },
    {
      "epoch": 0.2198665096191598,
      "grad_norm": 0.953125,
      "learning_rate": 0.00019888661338874803,
      "loss": 5.5142,
      "step": 70
    },
    {
      "epoch": 0.22300745975657638,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000198849263162441,
      "loss": 5.3004,
      "step": 71
    },
    {
      "epoch": 0.22614840989399293,
      "grad_norm": 0.7890625,
      "learning_rate": 0.0001988113003682161,
      "loss": 5.5914,
      "step": 72
    },
    {
      "epoch": 0.2292893600314095,
      "grad_norm": 0.71484375,
      "learning_rate": 0.00019877272524132847,
      "loss": 5.4175,
      "step": 73
    },
    {
      "epoch": 0.23243031016882607,
      "grad_norm": 0.99609375,
      "learning_rate": 0.00019873353802082771,
      "loss": 5.0854,
      "step": 74
    },
    {
      "epoch": 0.23557126030624265,
      "grad_norm": 1.046875,
      "learning_rate": 0.00019869373894955669,
      "loss": 5.5772,
      "step": 75
    },
    {
      "epoch": 0.2387122104436592,
      "grad_norm": 1.390625,
      "learning_rate": 0.00019865332827414988,
      "loss": 5.4289,
      "step": 76
    },
    {
      "epoch": 0.24185316058107578,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0001986123062450318,
      "loss": 5.5427,
      "step": 77
    },
    {
      "epoch": 0.24499411071849234,
      "grad_norm": 0.82421875,
      "learning_rate": 0.0001985706731164156,
      "loss": 5.3294,
      "step": 78
    },
    {
      "epoch": 0.24813506085590892,
      "grad_norm": 1.4921875,
      "learning_rate": 0.00019852842914630137,
      "loss": 5.3756,
      "step": 79
    },
    {
      "epoch": 0.25127601099332547,
      "grad_norm": 1.375,
      "learning_rate": 0.00019848557459647455,
      "loss": 5.4963,
      "step": 80
    },
    {
      "epoch": 0.25127601099332547,
      "eval_loss": 5.410098075866699,
      "eval_runtime": 66.9514,
      "eval_samples_per_second": 38.849,
      "eval_steps_per_second": 38.849,
      "step": 80
    },
    {
      "epoch": 0.254416961130742,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00019844210973250437,
      "loss": 5.4053,
      "step": 81
    },
    {
      "epoch": 0.25755791126815863,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0001983980348237422,
      "loss": 5.3084,
      "step": 82
    },
    {
      "epoch": 0.2606988614055752,
      "grad_norm": 0.95703125,
      "learning_rate": 0.00019835335014331976,
      "loss": 5.4774,
      "step": 83
    },
    {
      "epoch": 0.26383981154299174,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00019830805596814766,
      "loss": 5.3591,
      "step": 84
    },
    {
      "epoch": 0.2669807616804083,
      "grad_norm": 1.46875,
      "learning_rate": 0.00019826215257891342,
      "loss": 5.2504,
      "step": 85
    },
    {
      "epoch": 0.2701217118178249,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019821564026007988,
      "loss": 5.2333,
      "step": 86
    },
    {
      "epoch": 0.27326266195524146,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0001981685192998834,
      "loss": 5.4557,
      "step": 87
    },
    {
      "epoch": 0.276403612092658,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019812078999033222,
      "loss": 5.5066,
      "step": 88
    },
    {
      "epoch": 0.2795445622300746,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00019807245262720426,
      "loss": 5.3617,
      "step": 89
    },
    {
      "epoch": 0.2826855123674912,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0001980235075100458,
      "loss": 5.4076,
      "step": 90
    },
    {
      "epoch": 0.28582646250490773,
      "grad_norm": 0.921875,
      "learning_rate": 0.00019797395494216923,
      "loss": 5.2482,
      "step": 91
    },
    {
      "epoch": 0.2889674126423243,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00019792379523065126,
      "loss": 5.1448,
      "step": 92
    },
    {
      "epoch": 0.2921083627797409,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001978730286863312,
      "loss": 5.2483,
      "step": 93
    },
    {
      "epoch": 0.29524931291715745,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0001978216556238088,
      "loss": 5.1698,
      "step": 94
    },
    {
      "epoch": 0.298390263054574,
      "grad_norm": 0.91015625,
      "learning_rate": 0.00019776967636144245,
      "loss": 5.3225,
      "step": 95
    },
    {
      "epoch": 0.30153121319199055,
      "grad_norm": 0.80859375,
      "learning_rate": 0.00019771709122134713,
      "loss": 5.3077,
      "step": 96
    },
    {
      "epoch": 0.30467216332940716,
      "grad_norm": 0.76953125,
      "learning_rate": 0.00019766390052939242,
      "loss": 5.2636,
      "step": 97
    },
    {
      "epoch": 0.3078131134668237,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00019761010461520054,
      "loss": 5.4547,
      "step": 98
    },
    {
      "epoch": 0.31095406360424027,
      "grad_norm": 0.85546875,
      "learning_rate": 0.0001975557038121442,
      "loss": 5.2564,
      "step": 99
    },
    {
      "epoch": 0.3140950137416568,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00019750069845734473,
      "loss": 4.9768,
      "step": 100
    },
    {
      "epoch": 0.31723596387907343,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00019744508889166966,
      "loss": 5.2283,
      "step": 101
    },
    {
      "epoch": 0.32037691401649,
      "grad_norm": 1.34375,
      "learning_rate": 0.00019738887545973102,
      "loss": 5.4258,
      "step": 102
    },
    {
      "epoch": 0.32351786415390654,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00019733205850988285,
      "loss": 5.2331,
      "step": 103
    },
    {
      "epoch": 0.32665881429132315,
      "grad_norm": 0.828125,
      "learning_rate": 0.00019727463839421926,
      "loss": 5.1852,
      "step": 104
    },
    {
      "epoch": 0.3297997644287397,
      "grad_norm": 1.109375,
      "learning_rate": 0.00019721661546857213,
      "loss": 5.4063,
      "step": 105
    },
    {
      "epoch": 0.33294071456615626,
      "grad_norm": 0.8359375,
      "learning_rate": 0.000197157990092509,
      "loss": 5.2671,
      "step": 106
    },
    {
      "epoch": 0.3360816647035728,
      "grad_norm": 0.94140625,
      "learning_rate": 0.00019709876262933066,
      "loss": 5.3544,
      "step": 107
    },
    {
      "epoch": 0.3392226148409894,
      "grad_norm": 0.9609375,
      "learning_rate": 0.0001970389334460692,
      "loss": 5.1728,
      "step": 108
    },
    {
      "epoch": 0.342363564978406,
      "grad_norm": 0.921875,
      "learning_rate": 0.00019697850291348548,
      "loss": 5.3887,
      "step": 109
    },
    {
      "epoch": 0.34550451511582253,
      "grad_norm": 0.8984375,
      "learning_rate": 0.00019691747140606692,
      "loss": 5.1095,
      "step": 110
    },
    {
      "epoch": 0.3486454652532391,
      "grad_norm": 0.96875,
      "learning_rate": 0.00019685583930202514,
      "loss": 5.1703,
      "step": 111
    },
    {
      "epoch": 0.3517864153906557,
      "grad_norm": 0.81640625,
      "learning_rate": 0.0001967936069832937,
      "loss": 5.17,
      "step": 112
    },
    {
      "epoch": 0.35492736552807225,
      "grad_norm": 1.0625,
      "learning_rate": 0.00019673077483552568,
      "loss": 5.0519,
      "step": 113
    },
    {
      "epoch": 0.3580683156654888,
      "grad_norm": 0.87109375,
      "learning_rate": 0.00019666734324809125,
      "loss": 5.186,
      "step": 114
    },
    {
      "epoch": 0.36120926580290535,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00019660331261407544,
      "loss": 5.0202,
      "step": 115
    },
    {
      "epoch": 0.36435021594032196,
      "grad_norm": 0.70703125,
      "learning_rate": 0.00019653868333027535,
      "loss": 5.1102,
      "step": 116
    },
    {
      "epoch": 0.3674911660777385,
      "grad_norm": 0.85546875,
      "learning_rate": 0.00019647345579719807,
      "loss": 5.1,
      "step": 117
    },
    {
      "epoch": 0.37063211621515507,
      "grad_norm": 1.078125,
      "learning_rate": 0.000196407630419058,
      "loss": 5.0466,
      "step": 118
    },
    {
      "epoch": 0.3737730663525716,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00019634120760377428,
      "loss": 5.3088,
      "step": 119
    },
    {
      "epoch": 0.37691401648998824,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00019627418776296858,
      "loss": 5.2293,
      "step": 120
    },
    {
      "epoch": 0.3800549666274048,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019620657131196208,
      "loss": 5.2738,
      "step": 121
    },
    {
      "epoch": 0.38319591676482134,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019613835866977335,
      "loss": 4.9497,
      "step": 122
    },
    {
      "epoch": 0.38633686690223795,
      "grad_norm": 0.9375,
      "learning_rate": 0.00019606955025911542,
      "loss": 5.2231,
      "step": 123
    },
    {
      "epoch": 0.3894778170396545,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00019600014650639333,
      "loss": 5.3426,
      "step": 124
    },
    {
      "epoch": 0.39261876717707106,
      "grad_norm": 0.76953125,
      "learning_rate": 0.00019593014784170153,
      "loss": 5.0717,
      "step": 125
    },
    {
      "epoch": 0.3957597173144876,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00019585955469882097,
      "loss": 5.1569,
      "step": 126
    },
    {
      "epoch": 0.3989006674519042,
      "grad_norm": 0.75390625,
      "learning_rate": 0.0001957883675152167,
      "loss": 4.9017,
      "step": 127
    },
    {
      "epoch": 0.4020416175893208,
      "grad_norm": 0.96484375,
      "learning_rate": 0.00019571658673203502,
      "loss": 5.1124,
      "step": 128
    },
    {
      "epoch": 0.40518256772673733,
      "grad_norm": 0.953125,
      "learning_rate": 0.00019564421279410075,
      "loss": 4.7849,
      "step": 129
    },
    {
      "epoch": 0.4083235178641539,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00019557124614991443,
      "loss": 5.1534,
      "step": 130
    },
    {
      "epoch": 0.4114644680015705,
      "grad_norm": 1.015625,
      "learning_rate": 0.00019549768725164967,
      "loss": 5.2731,
      "step": 131
    },
    {
      "epoch": 0.41460541813898705,
      "grad_norm": 1.0,
      "learning_rate": 0.00019542353655515023,
      "loss": 5.0467,
      "step": 132
    },
    {
      "epoch": 0.4177463682764036,
      "grad_norm": 0.8671875,
      "learning_rate": 0.00019534879451992728,
      "loss": 4.8911,
      "step": 133
    },
    {
      "epoch": 0.42088731841382016,
      "grad_norm": 0.875,
      "learning_rate": 0.00019527346160915646,
      "loss": 5.2338,
      "step": 134
    },
    {
      "epoch": 0.42402826855123676,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019519753828967508,
      "loss": 5.1705,
      "step": 135
    },
    {
      "epoch": 0.4271692186886533,
      "grad_norm": 0.96484375,
      "learning_rate": 0.00019512102503197923,
      "loss": 5.3178,
      "step": 136
    },
    {
      "epoch": 0.43031016882606987,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019504392231022076,
      "loss": 5.1462,
      "step": 137
    },
    {
      "epoch": 0.4334511189634865,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00019496623060220457,
      "loss": 5.0293,
      "step": 138
    },
    {
      "epoch": 0.43659206910090304,
      "grad_norm": 1.046875,
      "learning_rate": 0.00019488795038938536,
      "loss": 5.0523,
      "step": 139
    },
    {
      "epoch": 0.4397330192383196,
      "grad_norm": 1.7421875,
      "learning_rate": 0.00019480908215686486,
      "loss": 5.0893,
      "step": 140
    },
    {
      "epoch": 0.44287396937573614,
      "grad_norm": 0.79296875,
      "learning_rate": 0.00019472962639338875,
      "loss": 5.0682,
      "step": 141
    },
    {
      "epoch": 0.44601491951315275,
      "grad_norm": 1.265625,
      "learning_rate": 0.00019464958359134354,
      "loss": 5.1261,
      "step": 142
    },
    {
      "epoch": 0.4491558696505693,
      "grad_norm": 1.09375,
      "learning_rate": 0.00019456895424675382,
      "loss": 5.2513,
      "step": 143
    },
    {
      "epoch": 0.45229681978798586,
      "grad_norm": 0.87890625,
      "learning_rate": 0.00019448773885927877,
      "loss": 5.0248,
      "step": 144
    },
    {
      "epoch": 0.4554377699254024,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00019440593793220936,
      "loss": 4.9527,
      "step": 145
    },
    {
      "epoch": 0.458578720062819,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00019432355197246515,
      "loss": 5.1182,
      "step": 146
    },
    {
      "epoch": 0.4617196702002356,
      "grad_norm": 1.125,
      "learning_rate": 0.00019424058149059112,
      "loss": 5.043,
      "step": 147
    },
    {
      "epoch": 0.46486062033765213,
      "grad_norm": 0.98828125,
      "learning_rate": 0.00019415702700075453,
      "loss": 5.1351,
      "step": 148
    },
    {
      "epoch": 0.4680015704750687,
      "grad_norm": 1.234375,
      "learning_rate": 0.00019407288902074176,
      "loss": 5.0489,
      "step": 149
    },
    {
      "epoch": 0.4711425206124853,
      "grad_norm": 1.265625,
      "learning_rate": 0.00019398816807195498,
      "loss": 4.8494,
      "step": 150
    },
    {
      "epoch": 0.47428347074990185,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00019390286467940918,
      "loss": 5.196,
      "step": 151
    },
    {
      "epoch": 0.4774244208873184,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0001938169793717286,
      "loss": 4.9598,
      "step": 152
    },
    {
      "epoch": 0.48056537102473496,
      "grad_norm": 1.15625,
      "learning_rate": 0.0001937305126811437,
      "loss": 5.1067,
      "step": 153
    },
    {
      "epoch": 0.48370632116215156,
      "grad_norm": 0.7890625,
      "learning_rate": 0.0001936434651434876,
      "loss": 5.1599,
      "step": 154
    },
    {
      "epoch": 0.4868472712995681,
      "grad_norm": 1.109375,
      "learning_rate": 0.00019355583729819317,
      "loss": 4.9971,
      "step": 155
    },
    {
      "epoch": 0.48998822143698467,
      "grad_norm": 1.25,
      "learning_rate": 0.0001934676296882892,
      "loss": 5.0528,
      "step": 156
    },
    {
      "epoch": 0.4931291715744013,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00019337884286039746,
      "loss": 5.2021,
      "step": 157
    },
    {
      "epoch": 0.49627012171181784,
      "grad_norm": 1.015625,
      "learning_rate": 0.00019328947736472904,
      "loss": 4.7814,
      "step": 158
    },
    {
      "epoch": 0.4994110718492344,
      "grad_norm": 1.0,
      "learning_rate": 0.00019319953375508106,
      "loss": 5.0906,
      "step": 159
    },
    {
      "epoch": 0.5025520219866509,
      "grad_norm": 0.91015625,
      "learning_rate": 0.00019310901258883317,
      "loss": 5.0323,
      "step": 160
    },
    {
      "epoch": 0.5025520219866509,
      "eval_loss": 5.075822353363037,
      "eval_runtime": 66.934,
      "eval_samples_per_second": 38.859,
      "eval_steps_per_second": 38.859,
      "step": 160
    },
    {
      "epoch": 0.5056929721240675,
      "grad_norm": 0.921875,
      "learning_rate": 0.00019301791442694413,
      "loss": 5.1209,
      "step": 161
    },
    {
      "epoch": 0.508833922261484,
      "grad_norm": 2.765625,
      "learning_rate": 0.00019292623983394838,
      "loss": 5.0187,
      "step": 162
    },
    {
      "epoch": 0.5119748723989007,
      "grad_norm": 1.234375,
      "learning_rate": 0.0001928339893779525,
      "loss": 4.9584,
      "step": 163
    },
    {
      "epoch": 0.5151158225363173,
      "grad_norm": 1.28125,
      "learning_rate": 0.00019274116363063163,
      "loss": 4.9459,
      "step": 164
    },
    {
      "epoch": 0.5182567726737338,
      "grad_norm": 0.859375,
      "learning_rate": 0.00019264776316722603,
      "loss": 4.7699,
      "step": 165
    },
    {
      "epoch": 0.5213977228111504,
      "grad_norm": 1.0625,
      "learning_rate": 0.00019255378856653746,
      "loss": 5.0324,
      "step": 166
    },
    {
      "epoch": 0.5245386729485669,
      "grad_norm": 1.15625,
      "learning_rate": 0.00019245924041092562,
      "loss": 5.2702,
      "step": 167
    },
    {
      "epoch": 0.5276796230859835,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00019236411928630446,
      "loss": 5.0989,
      "step": 168
    },
    {
      "epoch": 0.5308205732234,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00019226842578213874,
      "loss": 4.7667,
      "step": 169
    },
    {
      "epoch": 0.5339615233608166,
      "grad_norm": 0.99609375,
      "learning_rate": 0.00019217216049144007,
      "loss": 4.8303,
      "step": 170
    },
    {
      "epoch": 0.5371024734982333,
      "grad_norm": 0.8984375,
      "learning_rate": 0.00019207532401076358,
      "loss": 5.0607,
      "step": 171
    },
    {
      "epoch": 0.5402434236356498,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00019197791694020396,
      "loss": 4.96,
      "step": 172
    },
    {
      "epoch": 0.5433843737730664,
      "grad_norm": 0.91796875,
      "learning_rate": 0.00019187993988339192,
      "loss": 5.0107,
      "step": 173
    },
    {
      "epoch": 0.5465253239104829,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0001917813934474903,
      "loss": 5.1961,
      "step": 174
    },
    {
      "epoch": 0.5496662740478995,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0001916822782431904,
      "loss": 5.0727,
      "step": 175
    },
    {
      "epoch": 0.552807224185316,
      "grad_norm": 1.203125,
      "learning_rate": 0.00019158259488470815,
      "loss": 4.8185,
      "step": 176
    },
    {
      "epoch": 0.5559481743227326,
      "grad_norm": 1.59375,
      "learning_rate": 0.00019148234398978038,
      "loss": 5.2447,
      "step": 177
    },
    {
      "epoch": 0.5590891244601492,
      "grad_norm": 1.25,
      "learning_rate": 0.0001913815261796609,
      "loss": 5.0844,
      "step": 178
    },
    {
      "epoch": 0.5622300745975658,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0001912801420791167,
      "loss": 5.0112,
      "step": 179
    },
    {
      "epoch": 0.5653710247349824,
      "grad_norm": 1.3671875,
      "learning_rate": 0.000191178192316424,
      "loss": 5.1335,
      "step": 180
    },
    {
      "epoch": 0.5685119748723989,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019107567752336458,
      "loss": 5.1664,
      "step": 181
    },
    {
      "epoch": 0.5716529250098155,
      "grad_norm": 0.90625,
      "learning_rate": 0.0001909725983352215,
      "loss": 4.9254,
      "step": 182
    },
    {
      "epoch": 0.574793875147232,
      "grad_norm": 0.8515625,
      "learning_rate": 0.00019086895539077562,
      "loss": 4.8303,
      "step": 183
    },
    {
      "epoch": 0.5779348252846486,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019076474933230116,
      "loss": 4.9595,
      "step": 184
    },
    {
      "epoch": 0.5810757754220651,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00019065998080556204,
      "loss": 5.0253,
      "step": 185
    },
    {
      "epoch": 0.5842167255594818,
      "grad_norm": 1.078125,
      "learning_rate": 0.00019055465045980782,
      "loss": 5.1003,
      "step": 186
    },
    {
      "epoch": 0.5873576756968983,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00019044875894776966,
      "loss": 4.9631,
      "step": 187
    },
    {
      "epoch": 0.5904986258343149,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019034230692565614,
      "loss": 4.9462,
      "step": 188
    },
    {
      "epoch": 0.5936395759717314,
      "grad_norm": 1.4453125,
      "learning_rate": 0.0001902352950531495,
      "loss": 4.8688,
      "step": 189
    },
    {
      "epoch": 0.596780526109148,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0001901277239934012,
      "loss": 5.1219,
      "step": 190
    },
    {
      "epoch": 0.5999214762465646,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00019001959441302806,
      "loss": 5.0382,
      "step": 191
    },
    {
      "epoch": 0.6030624263839811,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00018991090698210802,
      "loss": 4.9474,
      "step": 192
    },
    {
      "epoch": 0.6062033765213978,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00018980166237417606,
      "loss": 5.034,
      "step": 193
    },
    {
      "epoch": 0.6093443266588143,
      "grad_norm": 1.1875,
      "learning_rate": 0.00018969186126621996,
      "loss": 5.0142,
      "step": 194
    },
    {
      "epoch": 0.6124852767962309,
      "grad_norm": 1.203125,
      "learning_rate": 0.00018958150433867605,
      "loss": 4.7944,
      "step": 195
    },
    {
      "epoch": 0.6156262269336474,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0001894705922754252,
      "loss": 4.7905,
      "step": 196
    },
    {
      "epoch": 0.618767177071064,
      "grad_norm": 0.92578125,
      "learning_rate": 0.0001893591257637883,
      "loss": 4.8537,
      "step": 197
    },
    {
      "epoch": 0.6219081272084805,
      "grad_norm": 1.15625,
      "learning_rate": 0.00018924710549452232,
      "loss": 4.8625,
      "step": 198
    },
    {
      "epoch": 0.6250490773458971,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0001891345321618157,
      "loss": 5.1188,
      "step": 199
    },
    {
      "epoch": 0.6281900274833137,
      "grad_norm": 0.9921875,
      "learning_rate": 0.00018902140646328435,
      "loss": 4.7798,
      "step": 200
    },
    {
      "epoch": 0.6313309776207303,
      "grad_norm": 1.234375,
      "learning_rate": 0.0001889077290999671,
      "loss": 4.9184,
      "step": 201
    },
    {
      "epoch": 0.6344719277581469,
      "grad_norm": 1.375,
      "learning_rate": 0.00018879350077632143,
      "loss": 5.0932,
      "step": 202
    },
    {
      "epoch": 0.6376128778955634,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00018867872220021913,
      "loss": 4.9846,
      "step": 203
    },
    {
      "epoch": 0.64075382803298,
      "grad_norm": 1.3203125,
      "learning_rate": 0.00018856339408294202,
      "loss": 4.8107,
      "step": 204
    },
    {
      "epoch": 0.6438947781703965,
      "grad_norm": 1.0625,
      "learning_rate": 0.0001884475171391772,
      "loss": 4.9413,
      "step": 205
    },
    {
      "epoch": 0.6470357283078131,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00018833109208701298,
      "loss": 4.9209,
      "step": 206
    },
    {
      "epoch": 0.6501766784452296,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00018821411964793433,
      "loss": 4.8073,
      "step": 207
    },
    {
      "epoch": 0.6533176285826463,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00018809660054681823,
      "loss": 4.7729,
      "step": 208
    },
    {
      "epoch": 0.6564585787200629,
      "grad_norm": 1.046875,
      "learning_rate": 0.0001879785355119295,
      "loss": 5.0412,
      "step": 209
    },
    {
      "epoch": 0.6595995288574794,
      "grad_norm": 2.515625,
      "learning_rate": 0.0001878599252749159,
      "loss": 4.8707,
      "step": 210
    },
    {
      "epoch": 0.662740478994896,
      "grad_norm": 1.6015625,
      "learning_rate": 0.00018774077057080398,
      "loss": 4.6271,
      "step": 211
    },
    {
      "epoch": 0.6658814291323125,
      "grad_norm": 1.359375,
      "learning_rate": 0.00018762107213799427,
      "loss": 4.8702,
      "step": 212
    },
    {
      "epoch": 0.6690223792697291,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00018750083071825677,
      "loss": 4.8727,
      "step": 213
    },
    {
      "epoch": 0.6721633294071456,
      "grad_norm": 1.71875,
      "learning_rate": 0.0001873800470567264,
      "loss": 4.8376,
      "step": 214
    },
    {
      "epoch": 0.6753042795445622,
      "grad_norm": 1.7421875,
      "learning_rate": 0.00018725872190189827,
      "loss": 4.8666,
      "step": 215
    },
    {
      "epoch": 0.6784452296819788,
      "grad_norm": 1.1875,
      "learning_rate": 0.00018713685600562328,
      "loss": 5.038,
      "step": 216
    },
    {
      "epoch": 0.6815861798193954,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00018701445012310315,
      "loss": 4.9007,
      "step": 217
    },
    {
      "epoch": 0.684727129956812,
      "grad_norm": 1.1875,
      "learning_rate": 0.00018689150501288593,
      "loss": 4.8299,
      "step": 218
    },
    {
      "epoch": 0.6878680800942285,
      "grad_norm": 1.3125,
      "learning_rate": 0.00018676802143686126,
      "loss": 4.801,
      "step": 219
    },
    {
      "epoch": 0.6910090302316451,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00018664400016025568,
      "loss": 4.7097,
      "step": 220
    },
    {
      "epoch": 0.6941499803690616,
      "grad_norm": 1.6796875,
      "learning_rate": 0.00018651944195162778,
      "loss": 4.8088,
      "step": 221
    },
    {
      "epoch": 0.6972909305064782,
      "grad_norm": 1.25,
      "learning_rate": 0.0001863943475828636,
      "loss": 4.9253,
      "step": 222
    },
    {
      "epoch": 0.7004318806438948,
      "grad_norm": 1.40625,
      "learning_rate": 0.00018626871782917174,
      "loss": 4.8615,
      "step": 223
    },
    {
      "epoch": 0.7035728307813114,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00018614255346907855,
      "loss": 4.7592,
      "step": 224
    },
    {
      "epoch": 0.7067137809187279,
      "grad_norm": 1.5,
      "learning_rate": 0.0001860158552844233,
      "loss": 4.6569,
      "step": 225
    },
    {
      "epoch": 0.7098547310561445,
      "grad_norm": 1.59375,
      "learning_rate": 0.0001858886240603534,
      "loss": 4.8259,
      "step": 226
    },
    {
      "epoch": 0.712995681193561,
      "grad_norm": 1.53125,
      "learning_rate": 0.00018576086058531957,
      "loss": 4.8066,
      "step": 227
    },
    {
      "epoch": 0.7161366313309776,
      "grad_norm": 1.3828125,
      "learning_rate": 0.00018563256565107072,
      "loss": 4.8039,
      "step": 228
    },
    {
      "epoch": 0.7192775814683942,
      "grad_norm": 1.390625,
      "learning_rate": 0.00018550374005264937,
      "loss": 4.8336,
      "step": 229
    },
    {
      "epoch": 0.7224185316058107,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0001853743845883865,
      "loss": 4.7032,
      "step": 230
    },
    {
      "epoch": 0.7255594817432274,
      "grad_norm": 1.5078125,
      "learning_rate": 0.0001852445000598966,
      "loss": 4.827,
      "step": 231
    },
    {
      "epoch": 0.7287004318806439,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0001851140872720729,
      "loss": 4.996,
      "step": 232
    },
    {
      "epoch": 0.7318413820180605,
      "grad_norm": 1.7109375,
      "learning_rate": 0.0001849831470330821,
      "loss": 4.7288,
      "step": 233
    },
    {
      "epoch": 0.734982332155477,
      "grad_norm": 1.6796875,
      "learning_rate": 0.00018485168015435966,
      "loss": 4.8204,
      "step": 234
    },
    {
      "epoch": 0.7381232822928936,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00018471968745060444,
      "loss": 4.8829,
      "step": 235
    },
    {
      "epoch": 0.7412642324303101,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00018458716973977405,
      "loss": 4.7297,
      "step": 236
    },
    {
      "epoch": 0.7444051825677267,
      "grad_norm": 1.6640625,
      "learning_rate": 0.00018445412784307932,
      "loss": 4.7916,
      "step": 237
    },
    {
      "epoch": 0.7475461327051433,
      "grad_norm": 1.265625,
      "learning_rate": 0.0001843205625849797,
      "loss": 4.5585,
      "step": 238
    },
    {
      "epoch": 0.7506870828425599,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00018418647479317776,
      "loss": 4.9319,
      "step": 239
    },
    {
      "epoch": 0.7538280329799765,
      "grad_norm": 1.6796875,
      "learning_rate": 0.00018405186529861416,
      "loss": 4.9877,
      "step": 240
    },
    {
      "epoch": 0.7538280329799765,
      "eval_loss": 4.841662406921387,
      "eval_runtime": 66.8839,
      "eval_samples_per_second": 38.888,
      "eval_steps_per_second": 38.888,
      "step": 240
    },
    {
      "epoch": 0.756968983117393,
      "grad_norm": 1.375,
      "learning_rate": 0.00018391673493546273,
      "loss": 4.7421,
      "step": 241
    },
    {
      "epoch": 0.7601099332548096,
      "grad_norm": 1.265625,
      "learning_rate": 0.00018378108454112494,
      "loss": 4.6469,
      "step": 242
    },
    {
      "epoch": 0.7632508833922261,
      "grad_norm": 2.109375,
      "learning_rate": 0.00018364491495622497,
      "loss": 4.7609,
      "step": 243
    },
    {
      "epoch": 0.7663918335296427,
      "grad_norm": 1.3203125,
      "learning_rate": 0.00018350822702460444,
      "loss": 4.737,
      "step": 244
    },
    {
      "epoch": 0.7695327836670592,
      "grad_norm": 1.7734375,
      "learning_rate": 0.0001833710215933171,
      "loss": 4.7964,
      "step": 245
    },
    {
      "epoch": 0.7726737338044759,
      "grad_norm": 1.6640625,
      "learning_rate": 0.00018323329951262367,
      "loss": 4.8785,
      "step": 246
    },
    {
      "epoch": 0.7758146839418925,
      "grad_norm": 1.7421875,
      "learning_rate": 0.0001830950616359865,
      "loss": 4.83,
      "step": 247
    },
    {
      "epoch": 0.778955634079309,
      "grad_norm": 1.53125,
      "learning_rate": 0.00018295630882006445,
      "loss": 4.9096,
      "step": 248
    },
    {
      "epoch": 0.7820965842167256,
      "grad_norm": 1.6484375,
      "learning_rate": 0.00018281704192470727,
      "loss": 4.7864,
      "step": 249
    },
    {
      "epoch": 0.7852375343541421,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00018267726181295065,
      "loss": 4.8557,
      "step": 250
    },
    {
      "epoch": 0.7883784844915587,
      "grad_norm": 2.578125,
      "learning_rate": 0.00018253696935101047,
      "loss": 4.8157,
      "step": 251
    },
    {
      "epoch": 0.7915194346289752,
      "grad_norm": 2.21875,
      "learning_rate": 0.00018239616540827782,
      "loss": 4.8016,
      "step": 252
    },
    {
      "epoch": 0.7946603847663918,
      "grad_norm": 1.390625,
      "learning_rate": 0.0001822548508573133,
      "loss": 4.657,
      "step": 253
    },
    {
      "epoch": 0.7978013349038084,
      "grad_norm": 2.21875,
      "learning_rate": 0.00018211302657384186,
      "loss": 4.7423,
      "step": 254
    },
    {
      "epoch": 0.800942285041225,
      "grad_norm": 2.328125,
      "learning_rate": 0.00018197069343674715,
      "loss": 4.8695,
      "step": 255
    },
    {
      "epoch": 0.8040832351786416,
      "grad_norm": 1.7421875,
      "learning_rate": 0.00018182785232806627,
      "loss": 4.9817,
      "step": 256
    },
    {
      "epoch": 0.8072241853160581,
      "grad_norm": 2.125,
      "learning_rate": 0.00018168450413298416,
      "loss": 4.794,
      "step": 257
    },
    {
      "epoch": 0.8103651354534747,
      "grad_norm": 1.9921875,
      "learning_rate": 0.00018154064973982816,
      "loss": 4.9111,
      "step": 258
    },
    {
      "epoch": 0.8135060855908912,
      "grad_norm": 2.0625,
      "learning_rate": 0.0001813962900400626,
      "loss": 4.9169,
      "step": 259
    },
    {
      "epoch": 0.8166470357283078,
      "grad_norm": 1.765625,
      "learning_rate": 0.00018125142592828307,
      "loss": 4.7243,
      "step": 260
    },
    {
      "epoch": 0.8197879858657244,
      "grad_norm": 2.234375,
      "learning_rate": 0.00018110605830221104,
      "loss": 4.8339,
      "step": 261
    },
    {
      "epoch": 0.822928936003141,
      "grad_norm": 1.9609375,
      "learning_rate": 0.00018096018806268834,
      "loss": 4.6423,
      "step": 262
    },
    {
      "epoch": 0.8260698861405575,
      "grad_norm": 1.9453125,
      "learning_rate": 0.00018081381611367134,
      "loss": 4.6603,
      "step": 263
    },
    {
      "epoch": 0.8292108362779741,
      "grad_norm": 2.359375,
      "learning_rate": 0.00018066694336222564,
      "loss": 4.8327,
      "step": 264
    },
    {
      "epoch": 0.8323517864153906,
      "grad_norm": 2.765625,
      "learning_rate": 0.0001805195707185202,
      "loss": 4.7741,
      "step": 265
    },
    {
      "epoch": 0.8354927365528072,
      "grad_norm": 2.453125,
      "learning_rate": 0.00018037169909582192,
      "loss": 4.8735,
      "step": 266
    },
    {
      "epoch": 0.8386336866902238,
      "grad_norm": 1.9375,
      "learning_rate": 0.00018022332941048972,
      "loss": 4.5862,
      "step": 267
    },
    {
      "epoch": 0.8417746368276403,
      "grad_norm": 2.453125,
      "learning_rate": 0.00018007446258196916,
      "loss": 4.6305,
      "step": 268
    },
    {
      "epoch": 0.844915586965057,
      "grad_norm": 1.8046875,
      "learning_rate": 0.00017992509953278644,
      "loss": 4.7259,
      "step": 269
    },
    {
      "epoch": 0.8480565371024735,
      "grad_norm": 1.9765625,
      "learning_rate": 0.000179775241188543,
      "loss": 4.7171,
      "step": 270
    },
    {
      "epoch": 0.8511974872398901,
      "grad_norm": 1.8984375,
      "learning_rate": 0.0001796248884779095,
      "loss": 4.5035,
      "step": 271
    },
    {
      "epoch": 0.8543384373773066,
      "grad_norm": 1.7265625,
      "learning_rate": 0.0001794740423326202,
      "loss": 4.5654,
      "step": 272
    },
    {
      "epoch": 0.8574793875147232,
      "grad_norm": 2.234375,
      "learning_rate": 0.00017932270368746723,
      "loss": 4.7109,
      "step": 273
    },
    {
      "epoch": 0.8606203376521397,
      "grad_norm": 2.09375,
      "learning_rate": 0.00017917087348029464,
      "loss": 4.6446,
      "step": 274
    },
    {
      "epoch": 0.8637612877895563,
      "grad_norm": 2.171875,
      "learning_rate": 0.0001790185526519928,
      "loss": 4.6444,
      "step": 275
    },
    {
      "epoch": 0.866902237926973,
      "grad_norm": 1.8984375,
      "learning_rate": 0.00017886574214649235,
      "loss": 4.6852,
      "step": 276
    },
    {
      "epoch": 0.8700431880643895,
      "grad_norm": 2.09375,
      "learning_rate": 0.0001787124429107585,
      "loss": 4.6116,
      "step": 277
    },
    {
      "epoch": 0.8731841382018061,
      "grad_norm": 1.875,
      "learning_rate": 0.00017855865589478515,
      "loss": 4.7119,
      "step": 278
    },
    {
      "epoch": 0.8763250883392226,
      "grad_norm": 2.0625,
      "learning_rate": 0.00017840438205158891,
      "loss": 4.7154,
      "step": 279
    },
    {
      "epoch": 0.8794660384766392,
      "grad_norm": 2.171875,
      "learning_rate": 0.00017824962233720332,
      "loss": 4.7945,
      "step": 280
    },
    {
      "epoch": 0.8826069886140557,
      "grad_norm": 2.828125,
      "learning_rate": 0.00017809437771067272,
      "loss": 4.7312,
      "step": 281
    },
    {
      "epoch": 0.8857479387514723,
      "grad_norm": 2.109375,
      "learning_rate": 0.00017793864913404663,
      "loss": 4.5674,
      "step": 282
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.203125,
      "learning_rate": 0.00017778243757237352,
      "loss": 4.6855,
      "step": 283
    },
    {
      "epoch": 0.8920298390263055,
      "grad_norm": 2.40625,
      "learning_rate": 0.00017762574399369485,
      "loss": 4.7105,
      "step": 284
    },
    {
      "epoch": 0.8951707891637221,
      "grad_norm": 2.171875,
      "learning_rate": 0.00017746856936903926,
      "loss": 4.7111,
      "step": 285
    },
    {
      "epoch": 0.8983117393011386,
      "grad_norm": 1.984375,
      "learning_rate": 0.0001773109146724163,
      "loss": 4.7511,
      "step": 286
    },
    {
      "epoch": 0.9014526894385552,
      "grad_norm": 2.34375,
      "learning_rate": 0.00017715278088081062,
      "loss": 4.7156,
      "step": 287
    },
    {
      "epoch": 0.9045936395759717,
      "grad_norm": 2.796875,
      "learning_rate": 0.0001769941689741758,
      "loss": 4.7225,
      "step": 288
    },
    {
      "epoch": 0.9077345897133883,
      "grad_norm": 2.703125,
      "learning_rate": 0.00017683507993542825,
      "loss": 4.7426,
      "step": 289
    },
    {
      "epoch": 0.9108755398508048,
      "grad_norm": 2.4375,
      "learning_rate": 0.0001766755147504412,
      "loss": 4.8524,
      "step": 290
    },
    {
      "epoch": 0.9140164899882215,
      "grad_norm": 2.65625,
      "learning_rate": 0.00017651547440803851,
      "loss": 4.6249,
      "step": 291
    },
    {
      "epoch": 0.917157440125638,
      "grad_norm": 3.125,
      "learning_rate": 0.00017635495989998864,
      "loss": 4.8815,
      "step": 292
    },
    {
      "epoch": 0.9202983902630546,
      "grad_norm": 2.71875,
      "learning_rate": 0.00017619397222099848,
      "loss": 4.7107,
      "step": 293
    },
    {
      "epoch": 0.9234393404004712,
      "grad_norm": 2.53125,
      "learning_rate": 0.00017603251236870702,
      "loss": 4.5988,
      "step": 294
    },
    {
      "epoch": 0.9265802905378877,
      "grad_norm": 2.703125,
      "learning_rate": 0.0001758705813436794,
      "loss": 4.43,
      "step": 295
    },
    {
      "epoch": 0.9297212406753043,
      "grad_norm": 2.84375,
      "learning_rate": 0.00017570818014940064,
      "loss": 4.8238,
      "step": 296
    },
    {
      "epoch": 0.9328621908127208,
      "grad_norm": 2.578125,
      "learning_rate": 0.00017554530979226933,
      "loss": 4.7022,
      "step": 297
    },
    {
      "epoch": 0.9360031409501374,
      "grad_norm": 2.96875,
      "learning_rate": 0.00017538197128159148,
      "loss": 4.8184,
      "step": 298
    },
    {
      "epoch": 0.939144091087554,
      "grad_norm": 2.609375,
      "learning_rate": 0.00017521816562957428,
      "loss": 4.4714,
      "step": 299
    },
    {
      "epoch": 0.9422850412249706,
      "grad_norm": 2.40625,
      "learning_rate": 0.00017505389385131972,
      "loss": 4.4407,
      "step": 300
    },
    {
      "epoch": 0.9454259913623871,
      "grad_norm": 3.25,
      "learning_rate": 0.00017488915696481838,
      "loss": 4.6623,
      "step": 301
    },
    {
      "epoch": 0.9485669414998037,
      "grad_norm": 2.109375,
      "learning_rate": 0.00017472395599094317,
      "loss": 4.6181,
      "step": 302
    },
    {
      "epoch": 0.9517078916372202,
      "grad_norm": 2.890625,
      "learning_rate": 0.00017455829195344293,
      "loss": 4.6449,
      "step": 303
    },
    {
      "epoch": 0.9548488417746368,
      "grad_norm": 6.84375,
      "learning_rate": 0.00017439216587893604,
      "loss": 4.538,
      "step": 304
    },
    {
      "epoch": 0.9579897919120534,
      "grad_norm": 3.5625,
      "learning_rate": 0.0001742255787969042,
      "loss": 4.7436,
      "step": 305
    },
    {
      "epoch": 0.9611307420494699,
      "grad_norm": 2.234375,
      "learning_rate": 0.00017405853173968589,
      "loss": 4.7237,
      "step": 306
    },
    {
      "epoch": 0.9642716921868866,
      "grad_norm": 2.3125,
      "learning_rate": 0.0001738910257424701,
      "loss": 4.5708,
      "step": 307
    },
    {
      "epoch": 0.9674126423243031,
      "grad_norm": 2.78125,
      "learning_rate": 0.00017372306184328985,
      "loss": 4.4765,
      "step": 308
    },
    {
      "epoch": 0.9705535924617197,
      "grad_norm": 2.109375,
      "learning_rate": 0.00017355464108301585,
      "loss": 4.6697,
      "step": 309
    },
    {
      "epoch": 0.9736945425991362,
      "grad_norm": 2.421875,
      "learning_rate": 0.00017338576450534984,
      "loss": 4.5376,
      "step": 310
    },
    {
      "epoch": 0.9768354927365528,
      "grad_norm": 2.671875,
      "learning_rate": 0.00017321643315681832,
      "loss": 4.7185,
      "step": 311
    },
    {
      "epoch": 0.9799764428739693,
      "grad_norm": 2.421875,
      "learning_rate": 0.000173046648086766,
      "loss": 4.6617,
      "step": 312
    },
    {
      "epoch": 0.9831173930113859,
      "grad_norm": 3.1875,
      "learning_rate": 0.00017287641034734934,
      "loss": 4.7403,
      "step": 313
    },
    {
      "epoch": 0.9862583431488026,
      "grad_norm": 2.21875,
      "learning_rate": 0.00017270572099352993,
      "loss": 4.5652,
      "step": 314
    },
    {
      "epoch": 0.9893992932862191,
      "grad_norm": 2.765625,
      "learning_rate": 0.000172534581083068,
      "loss": 4.5723,
      "step": 315
    },
    {
      "epoch": 0.9925402434236357,
      "grad_norm": 2.9375,
      "learning_rate": 0.00017236299167651593,
      "loss": 4.6485,
      "step": 316
    },
    {
      "epoch": 0.9956811935610522,
      "grad_norm": 3.109375,
      "learning_rate": 0.0001721909538372116,
      "loss": 4.5751,
      "step": 317
    },
    {
      "epoch": 0.9988221436984688,
      "grad_norm": 3.046875,
      "learning_rate": 0.0001720184686312718,
      "loss": 4.5623,
      "step": 318
    }
  ],
  "logging_steps": 1,
  "max_steps": 1272,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 318,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2355630330845594e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}